grimjim/Magot-v2-Gemma2-8k-9B-GGUF
Quantization vs grimjim/Magot-v2-Gemma2-8k-9B. grimjim/Magot-v2-Gemma2-8k-9B-GGUF is a GGUF quantization (Q8_0) of the same weights: 169 tensors match exactly and 295 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/169, MLP 0/126, Attention 0/168